From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757123AbbJIPen (ORCPT ); Fri, 9 Oct 2015 11:34:43 -0400 Received: from 8bytes.org ([81.169.241.247]:38846 "EHLO theia.8bytes.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756702AbbJIPem (ORCPT ); Fri, 9 Oct 2015 11:34:42 -0400 Date: Fri, 9 Oct 2015 17:34:40 +0200 From: Joerg Roedel To: Alex Williamson Cc: linux-kernel@vger.kernel.org, iommu@lists.linux-foundation.org, kvm@vger.kernel.org Subject: Re: BUG: unable to handle kernel paging request with v4.3-rc4 Message-ID: <20151009153440.GE27420@8bytes.org> References: <20151009145827.GB27420@8bytes.org> <1444404640.4059.219.camel@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1444404640.4059.219.camel@redhat.com> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Oct 09, 2015 at 09:30:40AM -0600, Alex Williamson wrote: > I have not seen this one yet. There literally have been no changes for > vfio in 4.3, so if this is new, it may be collateral from changes > elsewhere. 32bit devices really shouldn't make any difference to vfio, > I'll see if I can reproduce it myself though. Thanks, Great, thanks. It looks like some sort of memory corruption to me. What I did was trying to assign the 32bit dev together with its PCI bridge. Probing the bridge in VFIO fails due to the first check in the probe function and then I get the oops. I also tried assigning other bridges, or only the bridge to the 32bit bus, but this did not trigger the oops (but fails too, as it should). I'll also try to debug this more. Joerg